MAttNet icon indicating copy to clipboard operation
MAttNet copied to clipboard

MAttNet: Modular Attention Network for Referring Expression Comprehension

Results 23 MAttNet issues
Sort by recently updated
recently updated
newest added

I complied **mask-faster-rcnn** with command as following and got succeeded: ``` cd pyutils/mask-faster-rcnn/lib/ make ``` But I got some errors when I ran **MAttNet** project: ``` Traceback (most recent call...

Hi, I run the refcoco dataset with gt_boxes,but the val_acc is 78%.(I'm using python3)

Hi @lichengunc, Can you provide the link to the file data/feats/refcocog_umd/matt_res_det_feats.pth? Need that for [NMTree](https://github.com/daqingliu/NMTree) model and I am not able to find the file anywhere.

It gives a runtime error when I run the command `CUDA_VISIBLE_DEVICES=gpu_id python tools/extract_mrcn_det_feats.py --dataset refcoco --splitBy unc`. ***` RuntimeError: Dimension out of range (expected to be in range of [-2,...

RuntimeError: While copying the parameter named rpn_cls_score_net.weight, whose dimensions in the model are torch.Size([18, 512, 1, 1]) and whose dimensions in the checkpoint are torch.Size([24, 512, 1, 1]).

https://github.com/lichengunc/MAttNet/blob/de6f41ce5dc541425e5bd8ab96949ca09fb3de94/lib/layers/lang_encoder.py#L57 Hi, I find a mlp in the language encoder, which is used to project the original word embeddings into new representations. While it is not mentioned in the paper,...

Hello My name is Bela Chakraborty, an M.Phil student(pursuing) under A/PR Dr. Lei Wang at the University of Wollongong, NSW. I am very much interested in your MAttnet work and...

If we use the pretrained model for RefCOCO ((i.e., output/refcoco_unc/mrcn_cmr_with_st.pth) ) and execute the script experiments/scripts/eval_easy.sh", it throws an error saying that state-dict is missing a few keys. Could you...

Hi, is it possible to compute some kind of uncertainty about the answer given for a comprehension? Like for example if you query with an ambiguous expression or you query...

Running the demo `cv/example_demo.ipynb` with the original configuration and images from DAVIS2017 challenge and captions, give significantly different results than the Online Demo. For example, the first frame from `girl-dog`...